fofr/face-to-many 🔢🖼️❓📝 → 🖼️
About
Turn a face into 3D, emoji, pixel art, video game, claymation or toy
Example Output
Prompt:
"a person in a post apocalyptic war game"
Output
Performance Metrics
6.52s
Prediction Time
11.35s
Total Time
All Input Parameters
{
"image": "https://replicate.delivery/pbxt/KW7Getr2zD5ECxySdBZtLmPa322lNkXrpkMdKcmxeaDmq2b1/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
"style": "Clay",
"prompt": "a person in a post apocalyptic war game",
"lora_scale": 1,
"negative_prompt": "",
"prompt_strength": 4.5,
"denoising_strength": 0.65,
"instant_id_strength": 0.8,
"control_depth_strength": 0.8
}
Input Parameters
- seed
- Fix the random seed for reproducibility
- image
- An image of a person to be converted
- style
- Style to convert to
- prompt
- lora_scale
- How strong the LoRA will be
- custom_lora_url
- URL to a Replicate custom LoRA. Must be in the format https://replicate.delivery/pbxt/[id]/trained_model.tar or https://pbxt.replicate.delivery/[id]/trained_model.tar
- negative_prompt
- Things you do not want in the image
- prompt_strength
- Strength of the prompt. This is the CFG scale, higher numbers lead to stronger prompt, lower numbers will keep more of a likeness to the original.
- denoising_strength
- How much of the original image to keep. 1 is the complete destruction of the original image, 0 is the original image
- instant_id_strength
- How strong the InstantID will be.
- control_depth_strength
- Strength of depth controlnet. The bigger this is, the more controlnet affects the output.
Output Schema
Output
Example Execution Logs
Random seed set to: 2815191178
Checking inputs
✅ /tmp/inputs/input.webp
====================================
Running workflow
got prompt
Executing node 22, title: Load Image, class type: LoadImage
Executing node 67, title: 🔧 Image Resize, class type: ImageResize+
Executing node 3, title: LoRA Stacker, class type: LoRA Stacker
Executing node 49, title: AIO Aux Preprocessor, class type: AIO_Preprocessor
Executing node 28, title: Control Net Stacker, class type: Control Net Stacker
Executing node 2, title: Efficient Loader, class type: Efficient Loader
Requested to load SDXLClipModel
Loading 1 new model
----------------------------------------
[36mEfficient Loader Models Cache:[0m
Ckpt:
[1] albedobaseXL_v13
Lora:
[1] base_ckpt: albedobaseXL_v13
lora(mod,clip): ClayAnimationRedm(1.0,1.0)
Executing node 41, title: Apply InstantID, class type: ApplyInstantID
Executing node 51, title: VAE Encode, class type: VAEEncode
Executing node 4, title: KSampler (Efficient), class type: KSampler (Efficient)
Requested to load SDXL
Requested to load ControlNet
Requested to load ControlNet
Loading 3 new models
0%| | 0/17 [00:00<?, ?it/s]
6%|▌ | 1/17 [00:00<00:02, 6.37it/s]
12%|█▏ | 2/17 [00:00<00:02, 6.37it/s]
18%|█▊ | 3/17 [00:00<00:02, 6.36it/s]
24%|██▎ | 4/17 [00:00<00:02, 6.37it/s]
29%|██▉ | 5/17 [00:00<00:01, 6.36it/s]
35%|███▌ | 6/17 [00:00<00:01, 6.36it/s]
41%|████ | 7/17 [00:01<00:01, 6.36it/s]
47%|████▋ | 8/17 [00:01<00:01, 6.34it/s]
53%|█████▎ | 9/17 [00:01<00:01, 6.35it/s]
59%|█████▉ | 10/17 [00:01<00:01, 6.36it/s]
65%|██████▍ | 11/17 [00:01<00:00, 6.37it/s]
71%|███████ | 12/17 [00:01<00:00, 6.37it/s]
76%|███████▋ | 13/17 [00:02<00:00, 6.36it/s]
82%|████████▏ | 14/17 [00:02<00:00, 6.37it/s]
88%|████████▊ | 15/17 [00:02<00:00, 6.36it/s]
94%|█████████▍| 16/17 [00:02<00:00, 6.38it/s]
100%|██████████| 17/17 [00:02<00:00, 6.41it/s]
100%|██████████| 17/17 [00:02<00:00, 6.37it/s]
Executing node 5, title: Save Image, class type: SaveImage
Prompt executed in 6.08 seconds
outputs: {'4': {'images': []}, '5': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
Contents of /tmp/outputs:
ComfyUI_00001_.png
Version Details
- Version ID
a07f252abbbd832009640b27f063ea52d87d7a23a185ca165bec23b5adc8deaf- Version Created
- April 9, 2024